tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-08-09 16:24:38 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #4871 from BerriAI/litellm_addllama-3.1

Browse Source 
[Feat] Add Groq/llama3.1
This commit is contained in:
Ishaan Jaff
2024-07-24 20:54:59 -07:00
committed by GitHub
parent 3cd3491920 c08d4ca9ec
commit 7a97bf3aa9
3 changed files with 64 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/my-website/docs/providers/groq.md
+4 -1
View File
@@ -148,8 +148,11 @@ print(response)
## Supported Models - ALL Groq Models Supported!
We support ALL Groq models, just set `groq/` as a prefix when sending completion requests
| Model Name | Function Call |
| Model Name | Usage |
|--------------------|---------------------------------------------------------|
| llama-3.1-8b-instant | `completion(model="groq/llama-3.1-8b-instant", messages)` |
| llama-3.1-70b-versatile | `completion(model="groq/llama-3.1-70b-versatile", messages)` |
| llama-3.1-405b-reasoning | `completion(model="groq/llama-3.1-405b-reasoning", messages)` |
| llama3-8b-8192 | `completion(model="groq/llama3-8b-8192", messages)` |
| llama3-70b-8192 | `completion(model="groq/llama3-70b-8192", messages)` |
| llama2-70b-4096 | `completion(model="groq/llama2-70b-4096", messages)` |
litellm/model_prices_and_context_window_backup.json
+30
View File
@@ -1094,6 +1094,36 @@
"mode": "chat",
"supports_function_calling": true
},
"groq/llama-3.1-8b-instant": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"input_cost_per_token": 0.00000059,
"output_cost_per_token": 0.00000079,
"litellm_provider": "groq",
"mode": "chat",
"supports_function_calling": true
},
"groq/llama-3.1-70b-versatile": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"input_cost_per_token": 0.00000059,
"output_cost_per_token": 0.00000079,
"litellm_provider": "groq",
"mode": "chat",
"supports_function_calling": true
},
"groq/llama-3.1-405b-reasoning": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"input_cost_per_token": 0.00000059,
"output_cost_per_token": 0.00000079,
"litellm_provider": "groq",
"mode": "chat",
"supports_function_calling": true
},
"groq/mixtral-8x7b-32768": {
"max_tokens": 32768,
"max_input_tokens": 32768,
model_prices_and_context_window.json
+30
View File
@@ -1094,6 +1094,36 @@
"mode": "chat",
"supports_function_calling": true
},
"groq/llama-3.1-8b-instant": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"input_cost_per_token": 0.00000059,
"output_cost_per_token": 0.00000079,
"litellm_provider": "groq",
"mode": "chat",
"supports_function_calling": true
},
"groq/llama-3.1-70b-versatile": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"input_cost_per_token": 0.00000059,
"output_cost_per_token": 0.00000079,
"litellm_provider": "groq",
"mode": "chat",
"supports_function_calling": true
},
"groq/llama-3.1-405b-reasoning": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"input_cost_per_token": 0.00000059,
"output_cost_per_token": 0.00000079,
"litellm_provider": "groq",
"mode": "chat",
"supports_function_calling": true
},
"groq/mixtral-8x7b-32768": {
"max_tokens": 32768,
"max_input_tokens": 32768,